IP Library › Granted Patent US 12,725,491
Granted Patent B2
US 12,725,491 · App. 18/120,461 · Granted Sep 1, 2026

Remote validation of automated teller machines (ATMs) using machine learning

Inventors: Paul Mattison (Sherrills Ford, NC); Matthew Williams (Frisco, TX); Tanikia V. Simpson (Fairview Heights, IL); Kristi Kae Duncan (Fairview Heights, IL); Jeffrey A. Beacham (Charlotte, NC)
Assignee: Bank of America Corporation
G07F19/209G06N5/022G06Q10/20G06Q10/047
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,725,491
App. No.
18/120,461
Granted
Sep 1, 2026
Kind
B2
Abstract

Aspects of the disclosure relate to a remote validation platform for ATMs. The platform may train a reconfiguration model to output sets of configuration instructions. The platform may receive a first information stream from a first ATM. The platform may receive one or more additional information streams from sources associated with the first ATM. The platform may generate, using the reconfiguration model, a first set of configuration instructions based on the first information stream and the one or more additional information streams. The platform may cause reconfiguration of the first ATM based on the first set of configuration instructions. The platform may refine the reconfiguration model based on the first set of configuration instructions.

Claims (70)

1 . A computing platform comprising:

at least one processor;

a communication interface communicatively coupled to the at least one processor; and

memory storing computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:

train, based on historical configuration information, a reconfiguration model, wherein training the reconfiguration model configures the reconfiguration model to output, for an automated teller machine (ATM), sets of configuration instructions for modifying settings of cassettes of ATMs;

send, based on identifying that a predetermined period of time has elapsed, an automatic request for a first information stream from a first ATM comprising a plurality of cassettes, wherein each of the plurality of cassettes comprises a corresponding cassette mode;

receive, from the first ATM, the first information stream;

receive, from one or more sources associated with the first ATM, one or more additional information streams;

generate, based on inputting the first information stream and the one or more additional information streams into the reconfiguration model, a first set of configuration instructions for modifying settings of one or more cassettes of the first ATM;

cause, based on the first set of configuration instructions, reconfiguration of the first ATM, wherein the reconfiguration of the first ATM comprises one or more of:

setting, for one or more of the plurality of cassettes, one or more cassette thresholds, wherein each of the one or more cassette thresholds corresponds to a particular type of bill, or

modifying, for one or more of the plurality of cassettes, the corresponding cassette mode; and

refine the reconfiguration model by inputting the first set of configuration instructions into the reconfiguration model.

2 . The computing platform of claim 1 , wherein the one or more sources associated with the first ATM comprise one or more additional ATMs located within a predetermined proximity to the first ATM.

3 . The computing platform of claim 1 , wherein the one or more sources associated with the first ATM comprise one or more of:

weather reporting services, ATM servicing providers, financial institutions, event notification services, or community notification services.

4 . The computing platform of claim 1 , wherein the modifying of the corresponding cassette mode comprises, for one or more of the plurality of cassettes, changing the corresponding cassette mode to one of the following:

a recycle mode, a deposit mode, a withdrawal mode, or a reject mode.

5 . The computing platform of claim 1 , wherein the first information stream comprises one or more of:

one or more current bill counts, wherein each of the one or more current bill counts corresponds to a particular cassette of the plurality of cassettes,

one or more current bill thresholds, wherein each of the one or more current bill thresholds corresponds to a particular cassette of the plurality of cassettes, or

one or more current cassette modes, wherein each of the one or more current cassette modes corresponds to a particular cassette of the plurality of cassettes.

6 . The computing platform of claim 1 , wherein the one or more additional information streams comprises one or more:

one or more current bill thresholds corresponding to one or more additional ATMs, one or more current cassette modes corresponding to one or more additional ATMs, current weather information, servicing information corresponding to the first ATM, current event information for a geographical region corresponding to the first ATM, configuration preferences corresponding to a financial institution associated with the first ATM, or community information for a geographical region corresponding to the first ATM.

7 . The computing platform of claim 1 , wherein the memory stores additional computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:

receive, from an enterprise user device corresponding to an enterprise associated with the first ATM, a request to validate the first ATM; and

request, based on the request to validate the first ATM, the first information stream from the first ATM.

8 . The computing platform of claim 1 , wherein the memory stores additional computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:

identify, based on an updated information stream received from the first ATM, a reconfiguration result, wherein the reconfiguration result indicates whether or not the first ATM is validated.

9 . The computing platform of claim 8 , wherein the causing the reconfiguration of the first ATM is based on identifying that the reconfiguration result indicates that the first ATM is validated.

10 . The computing platform of claim 1 , wherein the memory stores additional computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:

cause, based on the first set of configuration instructions, a service device associated with the first ATM and different from the computing platform to update a service schedule corresponding to the first ATM; and

send, to the service device, one or more display commands, wherein the one or more display commands cause the service device to display a user interface comprising information of the first ATM and the updated service schedule.

11 . The computing platform of claim 1 , wherein the memory stores additional computer-readable instructions that, when executed by the at least one processor, cause the computing platform to cause, based on the first set of configuration instructions, an autonomous vehicle associated with a service provider corresponding to the first ATM to modify a service route corresponding to a plurality of ATMs.

12 . The computing platform of claim 1 , wherein the causing the reconfiguration of the first ATM comprises automatically reconfiguring the first ATM.

13 . The computing platform of claim 1 , wherein the causing the reconfiguration of the first ATM comprises:

sending, to an enterprise user device associated with the first ATM, one or more commands to display a user interface, wherein the user interface comprises the first set of configuration instructions and an updated information stream;

receiving, from the enterprise user device, an updated set of configuration instructions; and

reconfiguring, based on the updated set of configuration instructions, the first ATM.

14 . The computing platform of claim 1 , wherein the causing the reconfiguration of the first ATM comprises sending one or more commands from the computing platform to the first ATM to change a cassette mode of the one or more cassettes.

15 . A method comprising:

at a computing platform comprising at least one processor, a communication interface, and memory:

training, based on historical configuration information, a reconfiguration model, wherein training the reconfiguration model configures the reconfiguration model to output, for an automated teller machine (ATM), sets of configuration instructions for modifying settings of cassettes of ATMs;

sending, based on identifying that a predetermined period of time has elapsed, an automatic request for a first information stream from a first ATM comprising a plurality of cassettes, wherein each of the plurality of cassettes comprises a corresponding cassette mode;

receiving, from the first ATM, the first information stream;

receiving, from one or more sources associated with the first ATM, one or more additional information streams;

generating, based on inputting the first information stream and the one or more additional information streams into the reconfiguration model, a first set of configuration instructions for modifying settings of one or more cassettes of the first ATM;

causing, based on the first set of configuration instructions, reconfiguration of the first ATM, wherein the reconfiguration of the first ATM comprises one or more of:

setting, for one or more of the plurality of cassettes, one or more cassette thresholds, wherein each of the one or more cassette thresholds corresponds to a particular type of bill, or

modifying, for one or more of the plurality of cassettes, of the corresponding cassette mode; and

refining the reconfiguration model by inputting the first set of configuration instructions into the reconfiguration model.

16 . The method of claim 15 , wherein the one or more sources associated with the first ATM comprise one or more additional ATMs located within a predetermined proximity to the first ATM.

17 . The method of claim 15 , wherein the one or more sources associated with the first ATM comprise one or more of:

weather reporting services, ATM servicing providers, financial institutions, event notification services, or community notification services.

18 . The method of claim 15 , wherein the first information stream comprises one or more of:

one or more current bill counts, wherein each of the one or more current bill counts corresponds to a particular cassette of the plurality of cassettes,

one or more current bill thresholds, wherein each of the one or more current bill thresholds corresponds to a particular cassette of the plurality of cassettes, or

one or more current cassette modes, wherein each of the one or more current cassette modes corresponds to a particular cassette of the plurality of cassettes.

19 . The method of claim 15 , wherein the one or more additional information streams comprises one or more:

one or more current bill thresholds corresponding to one or more additional ATMs, one or more current cassette modes corresponding to one or more additional ATMs, current weather information, servicing information corresponding to the first ATM, current event information for a geographical region corresponding to the first ATM, configuration preferences corresponding to a financial institution associated with the first ATM, or community information for a geographical region corresponding to the first ATM.

20 . One or more non-transitory computer-readable media storing instructions that, when executed by a computing platform comprising at least one processor, a communication interface, and memory, cause the computing platform to:

train, based on historical configuration information, a reconfiguration model, wherein training the reconfiguration model configures the reconfiguration model to output, for an automated teller machine (ATM), sets of configuration instructions for modifying settings of cassettes of ATMs;

send, based on identifying that a predetermined period of time has elapsed, an automatic request for a first information stream from a first ATM comprising a plurality of cassettes, wherein each of the plurality of cassettes comprises a corresponding cassette mode;

receive, from the first ATM, the first information stream;

receive, from one or more sources associated with the first ATM, one or more additional information streams;

generate, based on inputting the first information stream and the one or more additional information streams into the reconfiguration model, a first set of configuration instructions for modifying settings of one or more cassettes of the first ATM;

cause, based on the first set of configuration instructions, reconfiguration of the first ATM, wherein the reconfiguration of the first ATM comprises one or more of:

setting, for one or more of the plurality of cassettes, one or more cassette thresholds, wherein each of the one or more cassette thresholds corresponds to a particular type of bill, or

modifying, for one or more of the plurality of cassettes, of the corresponding cassette mode; and

refine the reconfiguration model by inputting the first set of configuration instructions into the reconfiguration model.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 13, 2023
From: MATTISON, PAUL; WILLIAMS, MATTHEW; SIMPSON, TANIKIA V; DUNCAN, KRISTI KAE; BEACHAM, JEFFREY A
To: BANK OF AMERICA CORPORATION
Reel/Frame 062957/0618 →
Continuity (1)
Related Publication 20240312317A1 · Sep 19, 2024
References Cited (24)
US 11354403B1 · Ricket et al. · 2022 [cited by applicant]
US 11385623B2 · Cella et al. · 2022 [cited by applicant]
US 11507932B2 · Phillips et al. · 2022 [cited by applicant]
US 11526822B2 · Kochar et al. · 2022 [cited by applicant]
US 11543951B2 · Gervais et al. · 2023 [cited by applicant]
US 11550229B1 · Su et al. · 2023 [cited by applicant]
US 11556911B2 · Gottstein et al. · 2023 [cited by applicant]
US 11568331B2 · Volchegursky et al. · 2023 [cited by applicant]
US 11570016B2 · Johnson et al. · 2023 [cited by applicant]
US 11573643B2 · Singh · 2023 [cited by applicant]
US 11575684B2 · Alexander et al. · 2023 [cited by applicant]
US 11580229B2 · Ambekar et al. · 2023 [cited by applicant]
US 11586177B2 · Cella et al. · 2023 [cited by applicant]
US 11586178B2 · Cella et al. · 2023 [cited by applicant]
US 11586488B2 · Panda et al. · 2023 [cited by applicant]
US 20160379433A1 · Lavigne · 2016 [cited by examiner]
US 20220051209A1 · Kolls · 2022 [cited by examiner]
US 20230008226A1 · Delavari-Maraghi et al. · 2023 [cited by applicant]
US 20230015612A1 · Jung et al. · 2023 [cited by applicant]
US 20230032429A1 · Raj Susairaju et al. · 2023 [cited by applicant]
US 20230034548A1 · Deshmukh et al. · 2023 [cited by applicant]
US 20230052766A1 · Choe et al. · 2023 [cited by applicant]
CN 113191880A · 2021 [cited by examiner]
M. Asad, M. Shahzaib, Y. Abbasi and M. Rafi, “A Long-Short-Term-Memory Based Model for Predicting ATM Replenishment Amount,” 2020 21st International Arab Conference on Information Technology (ACIT), Giza, Egypt, 2020, p… [cited by examiner]